> I ran OCR in a few ways: First, using the built-in OCR of the circle-to-search feature on Android, which is often very good. Second, by using Tesseract with a few options and tweaks. And third by running it through Claude. After diffing the three to look for mismatches and getting Claude to output a table of locations for quick scanning, it became trivial but time-consuimg to tidy up the remainder
I bet 10$ I'd spend less time typing it from the t-shirt. And I wouldn't boil two kettles of water in the process.
But hey, AI makes you 10x more productive, I suppose
(Author here) for unrelated reasons my typing is very slow at the moment, so I was keen to automate. I see that people are getting different results from Claude than I did though.
You may want to retract that bet: https://news.ycombinator.com/item?id=48830846
Yeah, I read that later.
My bet is against manual OCR with various engines + finding mistakes later using an LLM.
I'd rather find the mistakes with my human brain. Keeps me limber. I might even accidentally learn something.